Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning

• URL: http://arxiv.org/abs/2605.13835v1
• Date: Wed, 13 May 2026 17:56:23 GMT
• Title: Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
• Abstract summary: We propose SPA (Semantic-guided Patch-level Alignment) for CLIP-based CIL.<n>For each class, we first construct representative and diverse visual samples and feed them to GPT-5.<n>These descriptions are used to guide the selection of discriminative patch-level visual features.
• Score: 13.950318836859731
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-Incremental Learning (CIL) enables models to continuously integrate new knowledge while mitigating catastrophic forgetting. Driven by the remarkable generalization of CLIP, leveraging pre-trained vision-language models has become a dominant paradigm in CIL. However, current work primarily focuses on aligning global image embeddings (i.e., [CLS] token) with their corresponding text prompts (i.e., [EOS] token). Despite their good performance, we find that they discard the rich patch-level semantic information inherent in CLIP's encoders. For instance, when recognizing a rabbit, local patches may encode its distinctive cues, such as long ears and a fluffy tail, which can provide complementary evidence for recognition. Based on the above observation, we propose SPA (Semantic-guided Patch-level Alignment) for CLIP-based CIL, which aims to awaken long-neglected local representations within CLIP. Specifically, for each class, we first construct representative and diverse visual samples and feed them to GPT-5 as visual guidance to generate class-wise semantic descriptions. These descriptions are used to guide the selection of discriminative patch-level visual features. Building upon these selected patches, we further employ optimal transport to align selected patch tokens with semantic tokens from class-wise descriptions, yielding a structured cross-modal alignment that improves recognition. Furthermore, we introduce task-specific projectors for effective adaptation to downstream incremental tasks, and sample pseudo-features from stored class-wise Gaussian statistics to calibrate old-class representations, thereby mitigating catastrophic forgetting. Extensive experiments demonstrate that SPA achieves state-of-the-art performance.

Related papers

• Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition [55.189113121465816]
  We propose a novel correlation adaptation prompt network (CAPNET) for long-tailed multi-label visual recognition.<n>CAPNET explicitly models correlations from CLIP's textual encoder.<n>It improves generalization through test-time ensembling and realigns visual-textual modalities.
  arXiv  Detail & Related papers  (2025-11-25T18:57:28Z)
• Hierarchical Representation Matching for CLIP-based Class-Incremental Learning [80.2317078787969]
  Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams.<n>Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task.<n>We introduce HiErarchical Representation MAtchiNg (HERMAN) for CLIP-based CIL.
  arXiv  Detail & Related papers  (2025-09-26T17:59:51Z)
• Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation [19.26516470653798]
  Weakly Supervised Semantic (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Maps (CAMs)<n>Recent methods primarily focus on image-text alignment for CAM generation, while CLIP's potential in patch-text alignment remains unexplored.<n>We propose ExCEL to explore CLIP's dense knowledge via a novel patchtext alignment paradigm for WSSS.
  arXiv  Detail & Related papers  (2025-03-26T02:00:49Z)
• CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections [22.32157080294386]
  We propose a label-free prompt-tuning method to enhance CLIP-based image classification performance using unlabeled images.<n>Our framework, NoLA (No Labels Attached), achieves an average absolute gain of 3.6% over the state-of-the-art LaFTer.
  arXiv  Detail & Related papers  (2024-11-28T19:48:54Z)
• Self-Calibrated CLIP for Training-Free Open-Vocabulary Segmentation [19.749490092520006]
  Self-Calibrated CLIP (SC-CLIP) is a training-free method that calibrates CLIP to produce finer representations.<n>SC-CLIP boosts the performance of vanilla CLIP ViT-L/14 by 6.8 times.
  arXiv  Detail & Related papers  (2024-11-24T15:14:05Z)
• TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training [29.431698321195814]
  Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. CLIP shows poor performance on multi-label datasets because the global feature tends to be dominated by the most prominent class. We propose a local-to-global framework to obtain image tags.
  arXiv  Detail & Related papers  (2023-12-20T08:15:40Z)
• CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement [65.47237619200442]
  Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. We augment CLIP training with task-specific vision models from model zoos to improve its visual representations. This simple setup shows substantial improvements of up to 16.3% across different vision tasks.
  arXiv  Detail & Related papers  (2023-10-21T20:20:13Z)
• MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation [90.73815426893034]
  We propose a transformer-based framework that aims to enhance weakly supervised semantic segmentation. We introduce a Multi-Class Token transformer, which incorporates multiple class tokens to enable class-aware interactions with the patch tokens. A Contrastive-Class-Token (CCT) module is proposed to enhance the learning of discriminative class tokens.
  arXiv  Detail & Related papers  (2023-08-06T03:30:20Z)
• Calibrating Class Activation Maps for Long-Tailed Visual Recognition [60.77124328049557]
  We present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map (CAMC) module to improve the learning and prediction of network classifiers. Second, we investigate the use of normalized classifiers for representation learning in long-tailed problems.
  arXiv  Detail & Related papers  (2021-08-29T05:45:03Z)
• SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption [72.35532598131176]
  We propose SCARF, a technique for contrastive learning, where views are formed by corrupting a random subset of features. We show that SCARF complements existing strategies and outperforms alternatives like autoencoders.
  arXiv  Detail & Related papers  (2021-06-29T08:08:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.